diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-22 10:46:44 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-22 10:46:44 -0800 |
| commit | ca78d3173cff3503bcd15723b049757f75762d15 (patch) | |
| tree | 8e5db7a3adbe3bcd3b08e6983a6e0f6becb0aaa0 /arch/arm64 | |
| parent | a4ee7bacd6c08479d56738456c07e4f32fc8e523 (diff) | |
| parent | ffe7afd1713558d73483834c2e2d03a1e39a4062 (diff) | |
| download | linux-ca78d3173cff3503bcd15723b049757f75762d15.tar.gz | |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon: - Errata workarounds for Qualcomm's Falkor CPU - Qualcomm L2 Cache PMU driver - Qualcomm SMCCC firmware quirk - Support for DEBUG_VIRTUAL - CPU feature detection for userspace via MRS emulation - Preliminary work for the Statistical Profiling Extension - Misc cleanups and non-critical fixes * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (74 commits) arm64/kprobes: consistently handle MRS/MSR with XZR arm64: cpufeature: correctly handle MRS to XZR arm64: traps: correctly handle MRS/MSR with XZR arm64: ptrace: add XZR-safe regs accessors arm64: include asm/assembler.h in entry-ftrace.S arm64: fix warning about swapper_pg_dir overflow arm64: Work around Falkor erratum 1003 arm64: head.S: Enable EL1 (host) access to SPE when entered at EL2 arm64: arch_timer: document Hisilicon erratum 161010101 arm64: use is_vmalloc_addr arm64: use linux/sizes.h for constants arm64: uaccess: consistently check object sizes perf: add qcom l2 cache perf events driver arm64: remove wrong CONFIG_PROC_SYSCTL ifdef ARM: smccc: Update HVC comment to describe new quirk parameter arm64: do not trace atomic operations ACPI/IORT: Fix the error return code in iort_add_smmu_platform_device() ACPI/IORT: Fix iort_node_get_id() mapping entries indexing arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA perf: xgene: Include module.h ...
Diffstat (limited to 'arch/arm64')
59 files changed, 945 insertions, 354 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 916024d6a2b1..a39029b5414e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -6,6 +6,7 @@ config ARM64 select ACPI_MCFG if ACPI select ACPI_SPCR_TABLE if ACPI select ARCH_CLOCKSOURCE_DATA + select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ELF_RANDOMIZE @@ -479,6 +480,34 @@ config CAVIUM_ERRATUM_27456 If unsure, say Y. +config QCOM_FALKOR_ERRATUM_1003 + bool "Falkor E1003: Incorrect translation due to ASID change" + default y + select ARM64_PAN if ARM64_SW_TTBR0_PAN + help + On Falkor v1, an incorrect ASID may be cached in the TLB when ASID + and BADDR are changed together in TTBRx_EL1. The workaround for this + issue is to use a reserved ASID in cpu_do_switch_mm() before + switching to the new ASID. Saying Y here selects ARM64_PAN if + ARM64_SW_TTBR0_PAN is selected. This is done because implementing and + maintaining the E1003 workaround in the software PAN emulation code + would be an unnecessary complication. The affected Falkor v1 CPU + implements ARMv8.1 hardware PAN support and using hardware PAN + support versus software PAN emulation is mutually exclusive at + runtime. + + If unsure, say Y. + +config QCOM_FALKOR_ERRATUM_1009 + bool "Falkor E1009: Prematurely complete a DSB after a TLBI" + default y + help + On Falkor v1, the CPU may prematurely complete a DSB following a + TLBI xxIS invalidate maintenance operation. Repeat the TLBI operation + one more time to fix the issue. + + If unsure, say Y. + endmenu @@ -614,6 +643,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK def_bool y depends on NUMA +config HOLES_IN_ZONE + def_bool y + depends on NUMA + source kernel/Kconfig.preempt source kernel/Kconfig.hz @@ -1010,7 +1043,7 @@ source "fs/Kconfig.binfmt" config COMPAT bool "Kernel support for 32-bit EL0" depends on ARM64_4K_PAGES || EXPERT - select COMPAT_BINFMT_ELF + select COMPAT_BINFMT_ELF if BINFMT_ELF select HAVE_UID16 select OLD_SIGSUSPEND3 select COMPAT_OLD_SIGACTION diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 560a8d85a4f8..fca2f02cde68 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -84,6 +84,14 @@ config DEBUG_ALIGN_RODATA If in doubt, say N. +config DEBUG_EFI + depends on EFI && DEBUG_INFO + bool "UEFI debugging" + help + Enable this option to include EFI specific debugging features into + the kernel that are only useful when using a debug build of the + UEFI firmware + source "drivers/hwtracing/coresight/Kconfig" endmenu diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3a4301163e04..1b67c3782d00 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -25,6 +25,7 @@ #include <asm/asm-offsets.h> #include <asm/cpufeature.h> +#include <asm/mmu_context.h> #include <asm/page.h> #include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> @@ -441,6 +442,28 @@ alternative_endif .endm /* + * Errata workaround prior to TTBR0_EL1 update + * + * val: TTBR value with new BADDR, preserved + * tmp0: temporary register, clobbered + * tmp1: other temporary register, clobbered + */ + .macro pre_ttbr0_update_workaround, val, tmp0, tmp1 +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 +alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003 + mrs \tmp0, ttbr0_el1 + mov \tmp1, #FALKOR_RESERVED_ASID + bfi \tmp0, \tmp1, #48, #16 // reserved ASID + old BADDR + msr ttbr0_el1, \tmp0 + isb + bfi \tmp0, \val, #0, #48 // reserved ASID + new BADDR + msr ttbr0_el1, \tmp0 + isb +alternative_else_nop_endif +#endif + .endm + +/* * Errata workaround post TTBR0_EL1 update. */ .macro post_ttbr0_update_workaround diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 4174f09678c4..fb78a5d3b60b 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -35,7 +35,9 @@ #define ARM64_HYP_OFFSET_LOW 14 #define ARM64_MISMATCHED_CACHE_LINE_SIZE 15 #define ARM64_HAS_NO_FPSIMD 16 +#define ARM64_WORKAROUND_REPEAT_TLBI 17 +#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18 -#define ARM64_NCAPS 17 +#define ARM64_NCAPS 19 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index b4989df48670..4ce82ed3e7c3 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -29,7 +29,20 @@ #include <linux/jump_label.h> #include <linux/kernel.h> -/* CPU feature register tracking */ +/* + * CPU feature register tracking + * + * The safe value of a CPUID feature field is dependent on the implications + * of the values assigned to it by the architecture. Based on the relationship + * between the values, the features are classified into 3 types - LOWER_SAFE, + * HIGHER_SAFE and EXACT. + * + * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest + * for HIGHER_SAFE. It is expected that all CPUs have the same value for + * a field when EXACT is specified, failing which, the safe value specified + * in the table is chosen. + */ + enum ftr_type { FTR_EXACT, /* Use a predefined safe value */ FTR_LOWER_SAFE, /* Smaller value is safe */ @@ -42,8 +55,12 @@ enum ftr_type { #define FTR_SIGNED true /* Value should be treated as signed */ #define FTR_UNSIGNED false /* Value should be treated as unsigned */ +#define FTR_VISIBLE true /* Feature visible to the user space */ +#define FTR_HIDDEN false /* Feature is hidden from the user */ + struct arm64_ftr_bits { bool sign; /* Value is signed ? */ + bool visible; bool strict; /* CPU Sanity check: strict matching required ? */ enum ftr_type type; u8 shift; @@ -59,7 +76,9 @@ struct arm64_ftr_bits { struct arm64_ftr_reg { const char *name; u64 strict_mask; + u64 user_mask; u64 sys_val; + u64 user_val; const struct arm64_ftr_bits *ftr_bits; }; @@ -159,6 +178,11 @@ static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp) return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); } +static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg) +{ + return (reg->user_val | (reg->sys_val & reg->user_mask)); +} + static inline int __attribute_const__ cpuid_feature_extract_field(u64 features, int field, bool sign) { diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 26a68ddb11c1..fc502713ab37 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -56,6 +56,9 @@ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) +#define MIDR_CPU_VAR_REV(var, rev) \ + (((var) << MIDR_VARIANT_SHIFT) | (rev)) + #define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ MIDR_ARCHITECTURE_MASK) @@ -71,6 +74,7 @@ #define ARM_CPU_IMP_APM 0x50 #define ARM_CPU_IMP_CAVIUM 0x43 #define ARM_CPU_IMP_BRCM 0x42 +#define ARM_CPU_IMP_QCOM 0x51 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -84,10 +88,13 @@ #define BRCM_CPU_PART_VULCAN 0x516 +#define QCOM_CPU_PART_FALKOR_V1 0x800 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) +#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index bc853663dd51..aecc07e09a18 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -332,6 +332,8 @@ bool aarch64_insn_is_branch(u32 insn); u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn); u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, u32 insn, u64 imm); +u32 aarch64_insn_decode_register(enum aarch64_insn_register_type type, + u32 insn); u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_branch_type type); u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr, diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 2a2752b5b6aa..6e99978e83bd 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -188,6 +188,9 @@ #define CPTR_EL2_DEFAULT 0x000033ff /* Hyp Debug Configuration Register bits */ +#define MDCR_EL2_TPMS (1 << 14) +#define MDCR_EL2_E2PB_MASK (UL(0x3)) +#define MDCR_EL2_E2PB_SHIFT (UL(12)) #define MDCR_EL2_TDRA (1 << 11) #define MDCR_EL2_TDOSA (1 << 10) #define MDCR_EL2_TDA (1 << 9) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e5050388e062..443b387021f2 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -229,7 +229,12 @@ struct kvm_vcpu_arch { /* Pointer to host CPU context */ kvm_cpu_context_t *host_cpu_context; - struct kvm_guest_debug_arch host_debug_state; + struct { + /* {Break,watch}point registers */ + struct kvm_guest_debug_arch regs; + /* Statistical profiling extension */ + u64 pmscr_el1; + } host_debug_state; /* VGIC state */ struct vgic_cpu vgic_cpu; diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 6f72fe8b0e3e..55772c13a375 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -47,7 +47,7 @@ * If the page is in the bottom half, we have to use the top half. If * the page is in the top half, we have to use the bottom half: * - * T = __virt_to_phys(__hyp_idmap_text_start) + * T = __pa_symbol(__hyp_idmap_text_start) * if (T & BIT(VA_BITS - 1)) * HYP_VA_MIN = 0 //idmap in upper half * else @@ -271,7 +271,7 @@ static inline void __kvm_flush_dcache_pud(pud_t pud) kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE); } -#define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x)) +#define kvm_virt_to_phys(x) __pa_symbol(x) void kvm_set_way_flush(struct kvm_vcpu *vcpu); void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index fc756e22c84c..606b20910a5c 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -19,7 +19,7 @@ __asm__(".arch_extension lse"); /* Move the ll/sc atomics out-of-line */ -#define __LL_SC_INLINE +#define __LL_SC_INLINE notrace #define __LL_SC_PREFIX(x) __ll_sc_##x #define __LL_SC_EXPORT(x) EXPORT_SYMBOL(__LL_SC_PREFIX(x)) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 90c39a662379..32f82723338a 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -102,25 +102,6 @@ #endif /* - * Physical vs virtual RAM address space conversion. These are - * private definitions which should NOT be used outside memory.h - * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. - */ -#define __virt_to_phys(x) ({ \ - phys_addr_t __x = (phys_addr_t)(x); \ - __x & BIT(VA_BITS - 1) ? (__x & ~PAGE_OFFSET) + PHYS_OFFSET : \ - (__x - kimage_voffset); }) - -#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) -#define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) - -/* - * Convert a page to/from a physical address - */ -#define page_to_phys(page) (__pfn_to_phys(page_to_pfn(page))) -#define phys_to_page(phys) (pfn_to_page(__phys_to_pfn(phys))) - -/* * Memory types available. */ #define MT_DEVICE_nGnRnE 0 @@ -187,6 +168,48 @@ static inline unsigned long kaslr_offset(void) #define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT) /* + * Physical vs virtual RAM address space conversion. These are + * private definitions which should NOT be used outside memory.h + * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. + */ + + +/* + * The linear kernel range starts in the middle of the virtual adddress + * space. Testing the top bit for the start of the region is a + * sufficient check. + */ +#define __is_lm_address(addr) (!!((addr) & BIT(VA_BITS - 1))) + +#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) +#define __kimg_to_phys(addr) ((addr) - kimage_voffset) + +#define __virt_to_phys_nodebug(x) ({ \ + phys_addr_t __x = (phys_addr_t)(x); \ + __is_lm_address(__x) ? __lm_to_phys(__x) : \ + __kimg_to_phys(__x); \ +}) + +#define __pa_symbol_nodebug(x) __kimg_to_phys((phys_addr_t)(x)) + +#ifdef CONFIG_DEBUG_VIRTUAL +extern phys_addr_t __virt_to_phys(unsigned long x); +extern phys_addr_t __phys_addr_symbol(unsigned long x); +#else +#define __virt_to_phys(x) __virt_to_phys_nodebug(x) +#define __phys_addr_symbol(x) __pa_symbol_nodebug(x) +#endif + +#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) +#define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) + +/* + * Convert a page to/from a physical address + */ +#define page_to_phys(page) (__pfn_to_phys(page_to_pfn(page))) +#define phys_to_page(phys) (pfn_to_page(__phys_to_pfn(phys))) + +/* * Note: Drivers should NOT use these. They are the wrong * translation for translating DMA addresses. Use the driver * DMA support - see dma-mapping.h. @@ -207,9 +230,12 @@ static inline void *phys_to_virt(phys_addr_t x) * Drivers should NOT use these either. */ #define __pa(x) __virt_to_phys((unsigned long)(x)) +#define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0)) +#define __pa_nodebug(x) __virt_to_phys_nodebug((unsigned long)(x)) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys(x)) +#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys((unsigned long)(x))) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) /* * virt_to_page(k) convert a _valid_ virtual address to struct page * diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 0363fe80455c..1ef40d82cfd3 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -19,6 +19,10 @@ #ifndef __ASM_MMU_CONTEXT_H #define __ASM_MMU_CONTEXT_H +#define FALKOR_RESERVED_ASID 1 + +#ifndef __ASSEMBLY__ + #include <linux/compiler.h> #include <linux/sched.h> @@ -45,7 +49,7 @@ static inline void contextidr_thread_switch(struct task_struct *next) */ static inline void cpu_set_reserved_ttbr0(void) { - unsigned long ttbr = virt_to_phys(empty_zero_page); + unsigned long ttbr = __pa_symbol(empty_zero_page); write_sysreg(ttbr, ttbr0_el1); isb(); @@ -114,7 +118,7 @@ static inline void cpu_install_idmap(void) local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); - cpu_switch_mm(idmap_pg_dir, &init_mm); + cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* @@ -129,7 +133,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgd) phys_addr_t pgd_phys = virt_to_phys(pgd); - replace_phys = (void *)virt_to_phys(idmap_cpu_replace_ttbr1); + replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); cpu_install_idmap(); replace_phys(pgd_phys); @@ -220,4 +224,6 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, void verify_cpu_asid_bits(void); -#endif +#endif /* !__ASSEMBLY__ */ + +#endif /* !__ASM_MMU_CONTEXT_H */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index ffbb9a520563..0eef6064bf3b 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -52,7 +52,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) pfn_to_page(PHYS_PFN(__pa(empty_zero_page))) +#define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) #define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte_val(pte)) @@ -71,9 +71,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) -#define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) +#define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) -#define pte_ng(pte) (!!(pte_val(pte) & PTE_NG)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -84,8 +83,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_global(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID) +/* + * Execute-only user mappings do not have the PTE_USER bit set. All valid + * kernel mappings have the PTE_UXN bit set. + */ +#define pte_valid_not_user(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) #define pte_valid_young(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) @@ -178,7 +181,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ - if (pte_valid_global(pte)) { + if (pte_valid_not_user(pte)) { dsb(ishst); isb(); } @@ -212,7 +215,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; - if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte)) + if (pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte, addr); } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 747c65a616ed..c97b8bd2acba 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -187,7 +187,6 @@ static inline void spin_lock_prefetch(const void *ptr) #endif int cpu_enable_pan(void *__unused); -int cpu_enable_uao(void *__unused); int cpu_enable_cache_maint_trap(void *__unused); #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 513daf050e84..11403fdd0a50 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -194,6 +194,26 @@ static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset) return val; } +/* + * Read a register given an architectural register index r. + * This handles the common case where 31 means XZR, not SP. + */ +static inline unsigned long pt_regs_read_reg(const struct pt_regs *regs, int r) +{ + return (r == 31) ? 0 : regs->regs[r]; +} + +/* + * Write a register given an architectural register index r. + * This handles the common case where 31 means XZR, not SP. + */ +static inline void pt_regs_write_reg(struct pt_regs *regs, int r, + unsigned long val) +{ + if (r != 31) + regs->regs[r] = val; +} + /* Valid only for Kernel mode traps. */ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 98ae03f8eedd..ac24b6e798b1 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -32,8 +32,27 @@ * [11-8] : CRm * [7-5] : Op2 */ +#define Op0_shift 19 +#define Op0_mask 0x3 +#define Op1_shift 16 +#define Op1_mask 0x7 +#define CRn_shift 12 +#define CRn_mask 0xf +#define CRm_shift 8 +#define CRm_mask 0xf +#define Op2_shift 5 +#define Op2_mask 0x7 + #define sys_reg(op0, op1, crn, crm, op2) \ - ((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5)) + (((op0) << Op0_shift) | ((op1) << Op1_shift) | \ + ((crn) << CRn_shift) | ((crm) << CRm_shift) | \ + ((op2) << Op2_shift)) + +#define sys_reg_Op0(id) (((id) >> Op0_shift) & Op0_mask) +#define sys_reg_Op1(id) (((id) >> Op1_shift) & Op1_mask) +#define sys_reg_CRn(id) (((id) >> CRn_shift) & CRn_mask) +#define sys_reg_CRm(id) (((id) >> CRm_shift) & CRm_mask) +#define sys_reg_Op2(id) (((id) >> Op2_shift) & Op2_mask) #ifndef CONFIG_BROKEN_GAS_INST @@ -190,6 +209,7 @@ #define ID_AA64MMFR2_CNP_SHIFT 0 /* id_aa64dfr0 */ +#define ID_AA64DFR0_PMSVER_SHIFT 32 #define ID_AA64DFR0_CTX_CMPS_SHIFT 28 #define ID_AA64DFR0_WRPS_SHIFT 20 #define ID_AA64DFR0_BRPS_SHIFT 12 @@ -245,6 +265,10 @@ #define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED #endif + +/* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ +#define SYS_MPIDR_SAFE_VAL (1UL << 31) + #ifdef __ASSEMBLY__ .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30 diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index deab52374119..af1c76981911 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -36,9 +36,21 @@ * not. The macros handles invoking the asm with or without the * register argument as appropriate. */ -#define __TLBI_0(op, arg) asm ("tlbi " #op) -#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0" : : "r" (arg)) -#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg) +#define __TLBI_0(op, arg) asm ("tlbi " #op "\n" \ + ALTERNATIVE("nop\n nop", \ + "dsb ish\n tlbi " #op, \ + ARM64_WORKAROUND_REPEAT_TLBI, \ + CONFIG_QCOM_FALKOR_ERRATUM_1009) \ + : : ) + +#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n" \ + ALTERNATIVE("nop\n nop", \ + "dsb ish\n tlbi " #op ", %0", \ + ARM64_WORKAROUND_REPEAT_TLBI, \ + CONFIG_QCOM_FALKOR_ERRATUM_1009) \ + : : "r" (arg)) + +#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg) #define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 46da3ea638bb..5308d696311b 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -379,9 +379,9 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u { unsigned long res = n; kasan_check_write(to, n); + check_object_size(to, n, false); if (access_ok(VERIFY_READ, from, n)) { - check_object_size(to, n, false); res = __arch_copy_from_user(to, from, n); } if (unlikely(res)) @@ -392,9 +392,9 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); + check_object_size(from, n, true); if (access_ok(VERIFY_WRITE, to, n)) { - check_object_size(from, n, true); n = __arch_copy_to_user(to, from, n); } return n; diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index a739287ef6a3..61c263cba272 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -30,5 +30,7 @@ #define HWCAP_ATOMICS (1 << 8) #define HWCAP_FPHP (1 << 9) #define HWCAP_ASIMDHP (1 << 10) +#define HWCAP_CPUID (1 << 11) +#define HWCAP_ASIMDRDM (1 << 12) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 7d66bbaafc0c..1606c6b2a280 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -55,3 +55,7 @@ obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) head-y := head.o extra-y += $(head-y) vmlinux.lds + +ifeq ($(CONFIG_DEBUG_EFI),y) +AFLAGS_head.o += -DVMLINUX_PATH="\"$(realpath $(objtree)/vmlinux)\"" +endif diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c index a32b4011d711..1f5655cd9cc9 100644 --- a/arch/arm64/kernel/acpi_parking_protocol.c +++ b/arch/arm64/kernel/acpi_parking_protocol.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ #include <linux/acpi.h> +#include <linux/mm.h> #include <linux/types.h> #include <asm/cpu_ops.h> @@ -109,7 +110,7 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu) * that read this address need to convert this address to the * Boot-Loader's endianness before jumping. */ - writeq_relaxed(__pa(secondary_entry), &mailbox->entry_point); + writeq_relaxed(__pa_symbol(secondary_entry), &mailbox->entry_point); writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id); arch_send_wakeup_ipi_mask(cpumask_of(cpu)); diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 78f368039c79..e9c4dc9e0ada 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -73,5 +73,5 @@ NOKPROBE_SYMBOL(_mcount); #endif /* arm-smccc */ -EXPORT_SYMBOL(arm_smccc_smc); -EXPORT_SYMBOL(arm_smccc_hvc); +EXPORT_SYMBOL(__arm_smccc_smc); +EXPORT_SYMBOL(__arm_smccc_hvc); diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index ecf9298a12d4..86032a012388 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -636,7 +636,7 @@ static int __init armv8_deprecated_init(void) if(system_supports_mixed_endian_el0()) register_insn_emulation(&setend_ops); else - pr_info("setend instruction emulation is not supported on the system"); + pr_info("setend instruction emulation is not supported on this system\n"); } cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING, diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index bc049afc73a7..b3bb7ef97bc8 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -143,8 +143,11 @@ int main(void) DEFINE(SLEEP_STACK_DATA_SYSTEM_REGS, offsetof(struct sleep_stack_data, system_regs)); DEFINE(SLEEP_STACK_DATA_CALLEE_REGS, offsetof(struct sleep_stack_data, callee_saved_regs)); #endif - DEFINE(ARM_SMCCC_RES_X0_OFFS, offsetof(struct arm_smccc_res, a0)); - DEFINE(ARM_SMCCC_RES_X2_OFFS, offsetof(struct arm_smccc_res, a2)); + DEFINE(ARM_SMCCC_RES_X0_OFFS, offsetof(struct arm_smccc_res, a0)); + DEFINE(ARM_SMCCC_RES_X2_OFFS, offsetof(struct arm_smccc_res, a2)); + DEFINE(ARM_SMCCC_QUIRK_ID_OFFS, offsetof(struct arm_smccc_quirk, id)); + DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS, offsetof(struct arm_smccc_quirk, state)); + BLANK(); DEFINE(HIBERN_PBE_ORIG, offsetof(struct pbe, orig_address)); DEFINE(HIBERN_PBE_ADDR, offsetof(struct pbe, address)); diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 9617301f76b5..3f2250fc391b 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -84,7 +84,7 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, static int __init_cache_level(unsigned int cpu) { - unsigned int ctype, level, leaves; + unsigned int ctype, level, leaves, of_level; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) { @@ -97,6 +97,17 @@ static int __init_cache_level(unsigned int cpu) leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; } + of_level = of_find_last_cache_level(cpu); + if (level < of_level) { + /* + * some external caches not specified in CLIDR_EL1 + * the information may be available in the device tree + * only unified external caches are considered here + */ + leaves += (of_level - level); + level = of_level; + } + this_cpu_ci->num_levels = level; this_cpu_ci->num_leaves = leaves; return 0; diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h index d4e9ecb264f0..6c2b1b4f57c9 100644 --- a/arch/arm64/kernel/cpu-reset.h +++ b/arch/arm64/kernel/cpu-reset.h @@ -24,7 +24,7 @@ static inline void __noreturn cpu_soft_restart(unsigned long el2_switch, el2_switch = el2_switch && !is_kernel_in_hyp_mode() && is_hyp_mode_available(); - restart = (void *)virt_to_phys(__cpu_soft_restart); + restart = (void *)__pa_symbol(__cpu_soft_restart); cpu_install_idmap(); restart(el2_switch, entry, arg0, arg1, arg2); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index b75e917aac46..f6cc67e7626e 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -79,8 +79,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A57 r0p0 - r1p2 */ .desc = "ARM erratum 832075", .capability = ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE, - MIDR_RANGE(MIDR_CORTEX_A57, 0x00, - (1 << MIDR_VARIANT_SHIFT) | 2), + MIDR_RANGE(MIDR_CORTEX_A57, + MIDR_CPU_VAR_REV(0, 0), + MIDR_CPU_VAR_REV(1, 2)), }, #endif #ifdef CONFIG_ARM64_ERRATUM_834220 @@ -88,8 +89,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A57 r0p0 - r1p2 */ .desc = "ARM erratum 834220", .capability = ARM64_WORKAROUND_834220, - MIDR_RANGE(MIDR_CORTEX_A57, 0x00, - (1 << MIDR_VARIANT_SHIFT) | 2), + MIDR_RANGE(MIDR_CORTEX_A57, + MIDR_CPU_VAR_REV(0, 0), + MIDR_CPU_VAR_REV(1, 2)), }, #endif #ifdef CONFIG_ARM64_ERRATUM_845719 @@ -113,8 +115,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cavium ThunderX, T88 pass 1.x - 2.1 */ .desc = "Cavium erratum 27456", .capability = ARM64_WORKAROUND_CAVIUM_27456, - MIDR_RANGE(MIDR_THUNDERX, 0x00, - (1 << MIDR_VARIANT_SHIFT) | 1), + MIDR_RANGE(MIDR_THUNDERX, + MIDR_CPU_VAR_REV(0, 0), + MIDR_CPU_VAR_REV(1, 1)), }, { /* Cavium ThunderX, T81 pass 1.0 */ @@ -130,6 +133,24 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .def_scope = SCOPE_LOCAL_CPU, .enable = cpu_enable_trap_ctr_access, }, +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 + { + .desc = "Qualcomm Technologies Falkor erratum 1003", + .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, + MIDR_RANGE(MIDR_QCOM_FALKOR_V1, + MIDR_CPU_VAR_REV(0, 0), + MIDR_CPU_VAR_REV(0, 0)), + }, +#endif +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009 + { + .desc = "Qualcomm Technologies Falkor erratum 1009", + .capability = ARM64_WORKAROUND_REPEAT_TLBI, + MIDR_RANGE(MIDR_QCOM_FALKOR_V1, + MIDR_CPU_VAR_REV(0, 0), + MIDR_CPU_VAR_REV(0, 0)), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index fdf8f045929f..abda8e861865 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -23,12 +23,14 @@ #include <linux/sort.h> #include <linux/stop_machine.h> #include <linux/types.h> +#include <linux/mm.h> #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> #include <asm/mmu_context.h> #include <asm/processor.h> #include <asm/sysreg.h> +#include <asm/traps.h> #include <asm/virt.h> unsigned long elf_hwcap __read_mostly; @@ -52,9 +54,10 @@ EXPORT_SYMBOL(cpu_hwcaps); DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS); EXPORT_SYMBOL(cpu_hwcap_keys); -#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ +#define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ .sign = SIGNED, \ + .visible = VISIBLE, \ .strict = STRICT, \ .type = TYPE, \ .shift = SHIFT, \ @@ -63,12 +66,12 @@ EXPORT_SYMBOL(cpu_hwcap_keys); } /* Define a feature with unsigned values */ -#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ - __ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) +#define ARM64_FTR_BITS(VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + __ARM64_FTR_BITS(FTR_UNSIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) /* Define a feature with a signed value */ -#define S_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ - __ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) +#define S_ARM64_FTR_BITS(VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + __ARM64_FTR_BITS(FTR_SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) #define ARM64_FTR_END \ { \ @@ -80,85 +83,80 @@ static bool __maybe_unused cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused); +/* + * NOTE: Any changes to the visibility of features should be kept in + * sync with the documentation of the CPU feature register ABI. + */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_AES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_AES_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0), - S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), - S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0), + S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), + S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), /* Linux doesn't care about the EL3 */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), - S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), - S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), /* Linux shouldn't care about secure memory */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0), /* * Differing PARange is fine as long as all peripherals and memory are mapped * within the minimum PARange of all CPUs */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_CNP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_CNP_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_ctr[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ /* * Linux can handle differing I-cache policies. Userspace JITs will * make use of *minLine. * If we have differing I-cache policies, report it as the weakest - AIVIVT. */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT), /* L1Ip */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT), /* L1Ip */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ ARM64_FTR_END, }; @@ -168,79 +166,78 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = { }; static const struct arm64_ftr_bits ftr_id_mmfr0[] = { - S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0xf), /* InnerShr */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */ - ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 4, 0), /* TCM */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* ShareLvl */ - S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0xf), /* OuterShr */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* PMSA */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* VMSA */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 28, 4, 0xf), /* InnerShr */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 16, 4, 0), /* TCM */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0), /* ShareLvl */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0xf), /* OuterShr */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* PMSA */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0), /* VMSA */ ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0), - S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 36, 28, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_PMSVER_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0), + /* + * We can instantiate multiple PMU instances with different levels + * of support. + */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_mvfr2[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */ ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_dczid[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 5, 27, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */ ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_isar5[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 20, 4, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_mmfr4[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */ ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_pfr0[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 16, 0), /* RAZ */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* State1 */ - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* State0 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 4, 4, 0), /* State1 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 4, 0), /* State0 */ ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_dfr0[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), - S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), ARM64_FTR_END, }; @@ -251,29 +248,24 @@ static const struct arm64_ftr_bits ftr_id_dfr0[] = { * id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] */ static const struct arm64_ftr_bits ftr_generic_32bits[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), - ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), ARM64_FTR_END, }; -static const struct arm64_ftr_bits ftr_generic[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0), +/* Table for a single 32bit feature value */ +static const struct arm64_ftr_bits ftr_single32[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 32, 0), ARM64_FTR_END, }; -static const struct arm64_ftr_bits ftr_generic32[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0), - ARM64_FTR_END, -}; - -static const struct arm64_ftr_bits ftr_aa64raz[] = { - ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0), +static const struct arm64_ftr_bits ftr_raz[] = { ARM64_FTR_END, }; @@ -314,15 +306,15 @@ static const struct __ftr_reg_entry { /* Op1 = 0, CRn = 0, CRm = 4 */ ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0), - ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_aa64raz), + ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), - ARM64_FTR_REG(SYS_ID_AA64DFR1_EL1, ftr_generic), + ARM64_FTR_REG(SYS_ID_AA64DFR1_EL1, ftr_raz), /* Op1 = 0, CRn = 0, CRm = 6 */ ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), - ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_aa64raz), + ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_raz), /* Op1 = 0, CRn = 0, CRm = 7 */ ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), @@ -334,7 +326,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid), /* Op1 = 3, CRn = 14, CRm = 0 */ - ARM64_FTR_REG(SYS_CNTFRQ_EL0, ftr_generic32), + ARM64_FTR_REG(SYS_CNTFRQ_EL0, ftr_single32), }; static int search_cmp_ftr_reg(const void *id, const void *regp) @@ -410,25 +402,43 @@ static void __init sort_ftr_regs(void) /* * Initialise the CPU feature register from Boot CPU values. * Also initiliases the strict_mask for the register. + * Any bits that are not covered by an arm64_ftr_bits entry are considered + * RES0 for the system-wide value, and must strictly match. */ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) { u64 val = 0; u64 strict_mask = ~0x0ULL; + u64 user_mask = 0; + u64 valid_mask = 0; + const struct arm64_ftr_bits *ftrp; struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg); BUG_ON(!reg); for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { + u64 ftr_mask = arm64_ftr_mask(ftrp); s64 ftr_new = arm64_ftr_value(ftrp, new); val = arm64_ftr_set_value(ftrp, val, ftr_new); + + valid_mask |= ftr_mask; if (!ftrp->strict) - strict_mask &= ~arm64_ftr_mask(ftrp); + strict_mask &= ~ftr_mask; + if (ftrp->visible) + user_mask |= ftr_mask; + else + reg->user_val = arm64_ftr_set_value(ftrp, + reg->user_val, + ftrp->safe_val); } + + val &= valid_mask; + reg->sys_val = val; reg->strict_mask = strict_mask; + reg->user_mask = user_mask; } void __init init_cpu_features(struct cpuinfo_arm64 *info) @@ -635,6 +645,9 @@ u64 read_system_reg(u32 id) return regp->sys_val; } +#define read_sysreg_case(r) \ + case r: return read_sysreg_s(r) + /* * __raw_read_system_reg() - Used by a STARTING cpu before cpuinfo is populated. * Read the system register on the current CPU @@ -642,36 +655,37 @@ u64 read_system_reg(u32 id) static u64 __raw_read_system_reg(u32 sys_id) { switch (sys_id) { - case SYS_ID_PFR0_EL1: return read_cpuid(ID_PFR0_EL1); - case SYS_ID_PFR1_EL1: return read_cpuid(ID_PFR1_EL1); - case SYS_ID_DFR0_EL1: return read_cpuid(ID_DFR0_EL1); - case SYS_ID_MMFR0_EL1: return read_cpuid(ID_MMFR0_EL1); - case SYS_ID_MMFR1_EL1: return read_cpuid(ID_MMFR1_EL1); - case SYS_ID_MMFR2_EL1: return read_cpuid(ID_MMFR2_EL1); - case SYS_ID_MMFR3_EL1: return read_cpuid(ID_MMFR3_EL1); - case SYS_ID_ISAR0_EL1: return read_cpuid(ID_ISAR0_EL1); - case SYS_ID_ISAR1_EL1: return read_cpuid(ID_ISAR1_EL1); - case SYS_ID_ISAR2_EL1: return read_cpuid(ID_ISAR2_EL1); - case SYS_ID_ISAR3_EL1: return read_cpuid(ID_ISAR3_EL1); - case SYS_ID_ISAR4_EL1: return read_cpuid(ID_ISAR4_EL1); - case SYS_ID_ISAR5_EL1: return read_cpuid(ID_ISAR4_EL1); - case SYS_MVFR0_EL1: return read_cpuid(MVFR0_EL1); - case SYS_MVFR1_EL1: return read_cpuid(MVFR1_EL1); - case SYS_MVFR2_EL1: return read_cpuid(MVFR2_EL1); - - case SYS_ID_AA64PFR0_EL1: return read_cpuid(ID_AA64PFR0_EL1); - case SYS_ID_AA64PFR1_EL1: return read_cpuid(ID_AA64PFR0_EL1); - case SYS_ID_AA64DFR0_EL1: return read_cpuid(ID_AA64DFR0_EL1); - case SYS_ID_AA64DFR1_EL1: return read_cpuid(ID_AA64DFR0_EL1); - case SYS_ID_AA64MMFR0_EL1: return read_cpuid(ID_AA64MMFR0_EL1); - case SYS_ID_AA64MMFR1_EL1: return read_cpuid(ID_AA64MMFR1_EL1); - case SYS_ID_AA64MMFR2_EL1: return read_cpuid(ID_AA64MMFR2_EL1); - case SYS_ID_AA64ISAR0_EL1: return read_cpuid(ID_AA64ISAR0_EL1); - case SYS_ID_AA64ISAR1_EL1: return read_cpuid(ID_AA64ISAR1_EL1); - - case SYS_CNTFRQ_EL0: return read_cpuid(CNTFRQ_EL0); - case SYS_CTR_EL0: return read_cpuid(CTR_EL0); - case SYS_DCZID_EL0: return read_cpuid(DCZID_EL0); + read_sysreg_case(SYS_ID_PFR0_EL1); + read_sysreg_case(SYS_ID_PFR1_EL1); + read_sysreg_case(SYS_ID_DFR0_EL1); + read_sysreg_case(SYS_ID_MMFR0_EL1); + read_sysreg_case(SYS_ID_MMFR1_EL1); + read_sysreg_case(SYS_ID_MMFR2_EL1); + read_sysreg_case(SYS_ID_MMFR3_EL1); + read_sysreg_case(SYS_ID_ISAR0_EL1); + read_sysreg_case(SYS_ID_ISAR1_EL1); + read_sysreg_case(SYS_ID_ISAR2_EL1); + read_sysreg_case(SYS_ID_ISAR3_EL1); + read_sysreg_case(SYS_ID_ISAR4_EL1); + read_sysreg_case(SYS_ID_ISAR5_EL1); + read_sysreg_case(SYS_MVFR0_EL1); + read_sysreg_case(SYS_MVFR1_EL1); + read_sysreg_case(SYS_MVFR2_EL1); + + read_sysreg_case(SYS_ID_AA64PFR0_EL1); + read_sysreg_case(SYS_ID_AA64PFR1_EL1); + read_sysreg_case(SYS_ID_AA64DFR0_EL1); + read_sysreg_case(SYS_ID_AA64DFR1_EL1); + read_sysreg_case(SYS_ID_AA64MMFR0_EL1); + read_sysreg_case(SYS_ID_AA64MMFR1_EL1); + read_sysreg_case(SYS_ID_AA64MMFR2_EL1); + read_sysreg_case(SYS_ID_AA64ISAR0_EL1); + read_sysreg_case(SYS_ID_AA64ISAR1_EL1); + + read_sysreg_case(SYS_CNTFRQ_EL0); + read_sysreg_case(SYS_CTR_EL0); + read_sysreg_case(SYS_DCZID_EL0); + default: BUG(); return 0; @@ -720,13 +734,11 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry, static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int __unused) { u32 midr = read_cpuid_id(); - u32 rv_min, rv_max; /* Cavium ThunderX pass 1.x and 2.x */ - rv_min = 0; - rv_max = (1 << MIDR_VARIANT_SHIFT) | MIDR_REVISION_MASK; - - return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX, rv_min, rv_max); + return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX, + MIDR_CPU_VAR_REV(0, 0), + MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK)); } static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused) @@ -737,7 +749,7 @@ static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry, int __unused) { - phys_addr_t idmap_addr = virt_to_phys(__hyp_idmap_text_start); + phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start); /* * Activate the lower HYP offset only if: @@ -806,7 +818,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR2_EL1, .field_pos = ID_AA64MMFR2_UAO_SHIFT, .min_field_value = 1, - .enable = cpu_enable_uao, + /* + * We rely on stop_machine() calling uao_thread_switch() to set + * UAO immediately after patching. + */ }, #endif /* CONFIG_ARM64_UAO */ #ifdef CONFIG_ARM64_PAN @@ -868,6 +883,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD), @@ -933,6 +949,8 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap) static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps) { + /* We support emulation of accesses to CPU ID feature registers */ + elf_hwcap |= HWCAP_CPUID; for (; hwcaps->matches; hwcaps++) if (hwcaps->matches(hwcaps, hwcaps->def_scope)) cap_set_elf_hwcap(hwcaps); @@ -1120,3 +1138,101 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) { return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO)); } + +/* + * We emulate only the following system register space. + * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7] + * See Table C5-6 System instruction encodings for System register accesses, + * ARMv8 ARM(ARM DDI 0487A.f) for more details. + */ +static inline bool __attribute_const__ is_emulated(u32 id) +{ + return (sys_reg_Op0(id) == 0x3 && + sys_reg_CRn(id) == 0x0 && + sys_reg_Op1(id) == 0x0 && + (sys_reg_CRm(id) == 0 || + ((sys_reg_CRm(id) >= 4) && (sys_reg_CRm(id) <= 7)))); +} + +/* + * With CRm == 0, reg should be one of : + * MIDR_EL1, MPIDR_EL1 or REVIDR_EL1. + */ +static inline int emulate_id_reg(u32 id, u64 *valp) +{ + switch (id) { + case SYS_MIDR_EL1: + *valp = read_cpuid_id(); + break; + case SYS_MPIDR_EL1: + *valp = SYS_MPIDR_SAFE_VAL; + break; + case SYS_REVIDR_EL1: + /* IMPLEMENTATION DEFINED values are emulated with 0 */ + *valp = 0; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int emulate_sys_reg(u32 id, u64 *valp) +{ + struct arm64_ftr_reg *regp; + + if (!is_emulated(id)) + return -EINVAL; + + if (sys_reg_CRm(id) == 0) + return emulate_id_reg(id, valp); + + regp = get_arm64_ftr_reg(id); + if (regp) + *valp = arm64_ftr_reg_user_value(regp); + else + /* + * The untracked registers are either IMPLEMENTATION DEFINED + * (e.g, ID_AFR0_EL1) or reserved RAZ. + */ + *valp = 0; + return 0; +} + +static int emulate_mrs(struct pt_regs *regs, u32 insn) +{ + int rc; + u32 sys_reg, dst; + u64 val; + + /* + * sys_reg values are defined as used in mrs/msr instruction. + * shift the imm value to get the encoding. + */ + sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5; + rc = emulate_sys_reg(sys_reg, &val); + if (!rc) { + dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn); + pt_regs_write_reg(regs, dst, val); + regs->pc += 4; + } + + return rc; +} + +static struct undef_hook mrs_hook = { + .instr_mask = 0xfff00000, + .instr_val = 0xd5300000, + .pstate_mask = COMPAT_PSR_MODE_MASK, + .pstate_val = PSR_MODE_EL0t, + .fn = emulate_mrs, +}; + +static int __init enable_mrs_emulation(void) +{ + register_undef_hook(&mrs_hook); + return 0; +} + +late_initcall(enable_mrs_emulation); diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 7b7be71e87bf..5b22c687f02a 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -63,6 +63,8 @@ static const char *const hwcap_str[] = { "atomics", "fphp", "asimdhp", + "cpuid", + "asimdrdm", NULL }; diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S index e88c064b845c..4e6ad355bd05 100644 --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -46,8 +46,7 @@ ENTRY(entry) * efi_system_table_t *sys_table, * unsigned long *image_addr) ; */ - adrp x8, _text - add x8, x8, #:lo12:_text + adr_l x8, _text add x2, sp, 16 str x8, [x2] bl efi_entry @@ -68,10 +67,8 @@ ENTRY(entry) /* * Calculate size of the kernel Image (same for original and copy). */ - adrp x1, _text - add x1, x1, #:lo12:_text - adrp x2, _edata - add x2, x2, #:lo12:_edata + adr_l x1, _text + adr_l x2, _edata sub x1, x2, x1 /* diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index aef02d2af3b5..e1be42e11ff5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -10,6 +10,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/insn.h> @@ -98,8 +99,7 @@ ENTRY(_mcount) mcount_enter - adrp x0, ftrace_trace_function - ldr x2, [x0, #:lo12:ftrace_trace_function] + ldr_l x2, ftrace_trace_function adr x0, ftrace_stub cmp x0, x2 // if (ftrace_trace_function b.eq skip_ftrace_call // != ftrace_stub) { @@ -115,15 +115,12 @@ skip_ftrace_call: // return; mcount_exit // return; // } skip_ftrace_call: - adrp x1, ftrace_graph_return - ldr x2, [x1, #:lo12:ftrace_graph_return] + ldr_l x2, ftrace_graph_return cmp x0, x2 // if ((ftrace_graph_return b.ne ftrace_graph_caller // != ftrace_stub) - adrp x1, ftrace_graph_entry // || (ftrace_graph_entry - adrp x0, ftrace_graph_entry_stub // != ftrace_graph_entry_stub)) - ldr x2, [x1, #:lo12:ftrace_graph_entry] - add x0, x0, #:lo12:ftrace_graph_entry_stub + ldr_l x2, ftrace_graph_entry // || (ftrace_graph_entry + adr_l x0, ftrace_graph_entry_stub // != ftrace_graph_entry_stub)) cmp x0, x2 b.ne ftrace_graph_caller // ftrace_graph_caller(); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 4b1abac3485a..4fb6ccd886d1 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -149,7 +149,7 @@ extra_header_fields: .quad 0 // SizeOfHeapReserve .quad 0 // SizeOfHeapCommit .long 0 // LoaderFlags - .long 0x6 // NumberOfRvaAndSizes + .long (section_table - .) / 8 // NumberOfRvaAndSizes .quad 0 // ExportTable .quad 0 // ImportTable @@ -158,6 +158,11 @@ extra_header_fields: .quad 0 // CertificationTable .quad 0 // BaseRelocationTable +#ifdef CONFIG_DEBUG_EFI + .long efi_debug_table - _head // DebugTable + .long efi_debug_table_size +#endif + // Section table section_table: @@ -195,6 +200,46 @@ section_table: .short 0 // NumberOfLineNumbers (0 for executables) .long 0xe0500020 // Characteristics (section flags) +#ifdef CONFIG_DEBUG_EFI + /* + * The debug table is referenced via its Relative Virtual Address (RVA), + * which is only defined for those parts of the image that are covered + * by a section declaration. Since this header is not covered by any + * section, the debug table must be emitted elsewhere. So stick it in + * the .init.rodata section instead. + * + * Note that the EFI debug entry itself may legally have a zero RVA, + * which means we can simply put it right after the section headers. + */ + __INITRODATA + + .align 2 +efi_debug_table: + // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long 2 // Type == EFI_IMAGE_DEBUG_TYPE_CODEVIEW + .long efi_debug_entry_size // SizeOfData + .long 0 // RVA + .long efi_debug_entry - _head // FileOffset + + .set efi_debug_table_size, . - efi_debug_table + .previous + +efi_debug_entry: + // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY + .ascii "NB10" // Signature + .long 0 // Unknown + .long 0 // Unknown2 + .long 0 // Unknown3 + + .asciz VMLINUX_PATH + + .set efi_debug_entry_size, . - efi_debug_entry +#endif + /* * EFI will load .text onwards at the 4k section alignment * described in the PE/COFF header. To ensure that instruction @@ -483,7 +528,7 @@ ENTRY(kimage_vaddr) * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. * - * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if + * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in w0 if * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) @@ -592,15 +637,26 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ - mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer - sbfx x0, x0, #8, #4 + mrs x1, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x1, #8, #4 cmp x0, #1 b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to 4: - csel x0, xzr, x0, lt // all PMU counters from EL1 - msr mdcr_el2, x0 // (if they exist) + csel x3, xzr, x0, lt // all PMU counters from EL1 + + /* Statistical profiling */ + ubfx x0, x1, #32, #4 // Check ID_AA64DFR0_EL1 PMSVer + cbz x0, 6f // Skip if SPE not present + cbnz x2, 5f // VHE? + mov x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) + orr x3, x3, x1 // If we don't have VHE, then + b 6f // use EL1&0 translation. +5: // For VHE, use EL2 translation + orr x3, x3, #MDCR_EL2_TPMS // and disable access from EL1 +6: + msr mdcr_el2, x3 // Configure debug traps /* Stage-2 translation */ msr vttbr_el2, xzr @@ -613,8 +669,7 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems install_el2_stub: /* Hypervisor stub */ - adrp x0, __hyp_stub_vectors - add x0, x0, #:lo12:__hyp_stub_vectors + adr_l x0, __hyp_stub_vectors msr vbar_el2, x0 /* spsr */ @@ -628,7 +683,7 @@ ENDPROC(el2_setup) /* * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed - * in x20. See arch/arm64/include/asm/virt.h for more info. + * in w0. See arch/arm64/include/asm/virt.h for more info. */ set_cpu_boot_mode_flag: adr_l x1, __boot_cpu_mode diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index fe301cbcb442..97a7384100f3 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -50,9 +50,6 @@ */ extern int in_suspend; -/* Find a symbols alias in the linear map */ -#define LMADDR(x) phys_to_virt(virt_to_phys(x)) - /* Do we need to reset el2? */ #define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode()) @@ -102,8 +99,8 @@ static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i) int pfn_is_nosave(unsigned long pfn) { - unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin); - unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1); + unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1); return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn); } @@ -125,12 +122,12 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) return -EOVERFLOW; arch_hdr_invariants(&hdr->invariants); - hdr->ttbr1_el1 = virt_to_phys(swapper_pg_dir); + hdr->ttbr1_el1 = __pa_symbol(swapper_pg_dir); hdr->reenter_kernel = _cpu_resume; /* We can't use __hyp_get_vectors() because kvm may still be loaded */ if (el2_reset_needed()) - hdr->__hyp_stub_vectors = virt_to_phys(__hyp_stub_vectors); + hdr->__hyp_stub_vectors = __pa_symbol(__hyp_stub_vectors); else hdr->__hyp_stub_vectors = 0; @@ -460,7 +457,6 @@ int swsusp_arch_resume(void) void *zero_page; size_t exit_size; pgd_t *tmp_pg_dir; - void *lm_restore_pblist; phys_addr_t phys_hibernate_exit; void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *, void *, phys_addr_t, phys_addr_t); @@ -472,7 +468,7 @@ int swsusp_arch_resume(void) */ tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); + pr_err("Failed to allocate memory for temporary page tables.\n"); rc = -ENOMEM; goto out; } @@ -481,18 +477,12 @@ int swsusp_arch_resume(void) goto out; /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - - /* * We need a zero page that is zero before & after resume in order to * to break before make on the ttbr1 page tables. */ zero_page = (void *)get_safe_page(GFP_ATOMIC); if (!zero_page) { - pr_err("Failed to allocate zero page."); + pr_err("Failed to allocate zero page.\n"); rc = -ENOMEM; goto out; } @@ -512,7 +502,7 @@ int swsusp_arch_resume(void) &phys_hibernate_exit, (void *)get_safe_page, GFP_ATOMIC); if (rc) { - pr_err("Failed to create safe executable page for hibernate_exit code."); + pr_err("Failed to create safe executable page for hibernate_exit code.\n"); goto out; } @@ -537,7 +527,7 @@ int swsusp_arch_resume(void) } hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, - resume_hdr.reenter_kernel, lm_restore_pblist, + resume_hdr.reenter_kernel, restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); out: diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 67f9cb9e8512..b6badff5a151 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -96,7 +96,7 @@ static void __kprobes *patch_map(void *addr, int fixmap) if (module && IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) page = vmalloc_to_page(addr); else if (!module) - page = pfn_to_page(PHYS_PFN(__pa(addr))); + page = phys_to_page(__pa_symbol(addr)); else return addr; @@ -417,6 +417,35 @@ u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, return insn; } +u32 aarch64_insn_decode_register(enum aarch64_insn_register_type type, + u32 insn) +{ + int shift; + + switch (type) { + case AARCH64_INSN_REGTYPE_RT: + case AARCH64_INSN_REGTYPE_RD: + shift = 0; + break; + case AARCH64_INSN_REGTYPE_RN: + shift = 5; + break; + case AARCH64_INSN_REGTYPE_RT2: + case AARCH64_INSN_REGTYPE_RA: + shift = 10; + break; + case AARCH64_INSN_REGTYPE_RM: + shift = 16; + break; + default: + pr_err("%s: unknown register type encoding %d\n", __func__, + type); + return 0; + } + + return (insn >> shift) & GENMASK(4, 0); +} + static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type, u32 insn, enum aarch64_insn_register reg) diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c index 357d3efe1366..be05868418ee 100644 --- a/arch/arm64/kernel/probes/simulate-insn.c +++ b/arch/arm64/kernel/probes/simulate-insn.c @@ -17,6 +17,8 @@ #include <linux/kernel.h> #include <linux/kprobes.h> +#include <asm/ptrace.h> + #include "simulate-insn.h" #define bbl_displacement(insn) \ @@ -36,30 +38,22 @@ static inline void set_x_reg(struct pt_regs *regs, int reg, u64 val) { - if (reg < 31) - regs->regs[reg] = val; + pt_regs_write_reg(regs, reg, val); } static inline void set_w_reg(struct pt_regs *regs, int reg, u64 val) { - if (reg < 31) - regs->regs[reg] = lower_32_bits(val); + pt_regs_write_reg(regs, reg, lower_32_bits(val)); } static inline u64 get_x_reg(struct pt_regs *regs, int reg) { - if (reg < 31) - return regs->regs[reg]; - else - return 0; + return pt_regs_read_reg(regs, reg); } static inline u32 get_w_reg(struct pt_regs *regs, int reg) { - if (reg < 31) - return lower_32_bits(regs->regs[reg]); - else - return 0; + return lower_32_bits(pt_regs_read_reg(regs, reg)); } static bool __kprobes check_cbz(u32 opcode, struct pt_regs *regs) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index a3a2816ba73a..1ad48f93abdd 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -339,7 +339,7 @@ static void entry_task_switch(struct task_struct *next) /* * Thread switching. */ -struct task_struct *__switch_to(struct task_struct *prev, +__notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next) { struct task_struct *last; @@ -407,7 +407,7 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { if (is_compat_task()) - return randomize_page(mm->brk, 0x02000000); + return randomize_page(mm->brk, SZ_32M); else - return randomize_page(mm->brk, 0x40000000); + return randomize_page(mm->brk, SZ_1G); } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 42816bebb1e0..e8edbf13302a 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -20,6 +20,7 @@ #include <linux/smp.h> #include <linux/delay.h> #include <linux/psci.h> +#include <linux/mm.h> #include <uapi/linux/psci.h> @@ -45,7 +46,7 @@ static int __init cpu_psci_cpu_prepare(unsigned int cpu) static int cpu_psci_cpu_boot(unsigned int cpu) { - int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry)); + int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa_symbol(secondary_entry)); if (err) pr_err("failed to boot CPU%d (%d)\n", cpu, err); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index b051367e2149..952e2c0dabd5 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -42,6 +42,7 @@ #include <linux/of_fdt.h> #include <linux/efi.h> #include <linux/psci.h> +#include <linux/mm.h> #include <asm/acpi.h> #include <asm/fixmap.h> @@ -199,16 +200,16 @@ static void __init request_standard_resources(void) struct memblock_region *region; struct resource *res; - kernel_code.start = virt_to_phys(_text); - kernel_code.end = virt_to_phys(__init_begin - 1); - kernel_data.start = virt_to_phys(_sdata); - kernel_data.end = virt_to_phys(_end - 1); + kernel_code.start = __pa_symbol(_text); + kernel_code.end = __pa_symbol(__init_begin - 1); + kernel_data.start = __pa_symbol(_sdata); + kernel_data.end = __pa_symbol(_end - 1); for_each_memblock(memory, region) { res = alloc_bootmem_low(sizeof(*res)); if (memblock_is_nomap(region)) { res->name = "reserved"; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_MEM; } else { res->name = "System RAM"; res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; @@ -297,7 +298,7 @@ void __init setup_arch(char **cmdline_p) * faults in case uaccess_enable() is inadvertently called by the init * thread. */ - init_task.thread_info.ttbr0 = virt_to_phys(empty_zero_page); + init_task.thread_info.ttbr0 = __pa_symbol(empty_zero_page); #endif #ifdef CONFIG_VT diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S index ae0496fa4235..62522342e1e4 100644 --- a/arch/arm64/kernel/smccc-call.S +++ b/arch/arm64/kernel/smccc-call.S @@ -12,6 +12,7 @@ * */ #include <linux/linkage.h> +#include <linux/arm-smccc.h> #include <asm/asm-offsets.h> .macro SMCCC instr @@ -20,24 +21,32 @@ ldr x4, [sp] stp x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS] stp x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS] - ret + ldr x4, [sp, #8] + cbz x4, 1f /* no quirk structure */ + ldr x9, [x4, #ARM_SMCCC_QUIRK_ID_OFFS] + cmp x9, #ARM_SMCCC_QUIRK_QCOM_A6 + b.ne 1f + str x6, [x4, ARM_SMCCC_QUIRK_STATE_OFFS] +1: ret .cfi_endproc .endm /* * void arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, * unsigned long a3, unsigned long a4, unsigned long a5, - * unsigned long a6, unsigned long a7, struct arm_smccc_res *res) + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res, + * struct arm_smccc_quirk *quirk) */ -ENTRY(arm_smccc_smc) +ENTRY(__arm_smccc_smc) SMCCC smc -ENDPROC(arm_smccc_smc) +ENDPROC(__arm_smccc_smc) /* * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, * unsigned long a3, unsigned long a4, unsigned long a5, - * unsigned long a6, unsigned long a7, struct arm_smccc_res *res) + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res, + * struct arm_smccc_quirk *quirk) */ -ENTRY(arm_smccc_hvc) +ENTRY(__arm_smccc_hvc) SMCCC hvc -ENDPROC(arm_smccc_hvc) +ENDPROC(__arm_smccc_hvc) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index cb87234cfcf2..a8ec5da530af 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -603,9 +603,9 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, */ static void __init of_parse_and_init_cpus(void) { - struct device_node *dn = NULL; + struct device_node *dn; - while ((dn = of_find_node_by_type(dn, "cpu"))) { + for_each_node_by_type(dn, "cpu") { u64 hwid = of_get_cpu_mpidr(dn); if (hwid == INVALID_HWID) diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index 9a00eee9acc8..93034651c87e 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -21,6 +21,7 @@ #include <linux/of.h> #include <linux/smp.h> #include <linux/types.h> +#include <linux/mm.h> #include <asm/cacheflush.h> #include <asm/cpu_ops.h> @@ -98,7 +99,7 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu) * boot-loader's endianess before jumping. This is mandated by * the boot protocol. */ - writeq_relaxed(__pa(secondary_holding_pen), release_addr); + writeq_relaxed(__pa_symbol(secondary_holding_pen), release_addr); __flush_dcache_area((__force void *)release_addr, sizeof(*release_addr)); diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 655e65f38f31..565dd69888cc 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -41,7 +41,6 @@ static void set_capacity_scale(unsigned int cpu, unsigned long capacity) per_cpu(cpu_scale, cpu) = capacity; } -#ifdef CONFIG_PROC_SYSCTL static ssize_t cpu_capacity_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -98,7 +97,6 @@ static int register_cpu_capacity_sysctl(void) return 0; } subsys_initcall(register_cpu_capacity_sysctl); -#endif static u32 capacity_scale; static u32 *raw_capacity; diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 659b2e6b6cf7..7d47c2cdfd93 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -466,7 +466,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; int ret = 0; - address = (rt == 31) ? 0 : regs->regs[rt]; + address = pt_regs_read_reg(regs, rt); switch (crm) { case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */ @@ -495,8 +495,10 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) { int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT; + unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); + + pt_regs_write_reg(regs, rt, val); - regs->regs[rt] = arm64_ftr_reg_ctrel0.sys_val; regs->pc += 4; } @@ -531,7 +533,12 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) return; } - force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); + /* + * New SYS instructions may previously have been undefined at EL0. Fall + * back to our usual undefined instruction handler so that we handle + * these consistently. + */ + do_undefinstr(regs); } long compat_arm_syscall(struct pt_regs *regs); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index a2c2478e7d78..41b6e31f8f55 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -123,6 +123,7 @@ static int __init vdso_init(void) { int i; struct page **vdso_pagelist; + unsigned long pfn; if (memcmp(&vdso_start, "\177ELF", 4)) { pr_err("vDSO is not a valid ELF object!\n"); @@ -140,11 +141,14 @@ static int __init vdso_init(void) return -ENOMEM; /* Grab the vDSO data page. */ - vdso_pagelist[0] = pfn_to_page(PHYS_PFN(__pa(vdso_data))); + vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data)); + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(&vdso_start); + for (i = 0; i < vdso_pages; i++) - vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(&vdso_start)) + i); + vdso_pagelist[i + 1] = pfn_to_page(pfn + i); vdso_spec[0].pages = &vdso_pagelist[0]; vdso_spec[1].pages = &vdso_pagelist[1]; diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 47e5f0feaee8..dbadfaf850a7 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -95,6 +95,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) + * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY @@ -110,8 +111,13 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); + /* + * This also clears MDCR_EL2_E2PB_MASK to disable guest access + * to the profiling buffer. + */ vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | + MDCR_EL2_TPMS | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 4ba5c9095d03..f5154ed3da6c 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -65,6 +65,66 @@ default: write_debug(ptr[0], reg, 0); \ } +#define PMSCR_EL1 sys_reg(3, 0, 9, 9, 0) + +#define PMBLIMITR_EL1 sys_reg(3, 0, 9, 10, 0) +#define PMBLIMITR_EL1_E BIT(0) + +#define PMBIDR_EL1 sys_reg(3, 0, 9, 10, 7) +#define PMBIDR_EL1_P BIT(4) + +#define psb_csync() asm volatile("hint #17") + +static void __hyp_text __debug_save_spe_vhe(u64 *pmscr_el1) +{ + /* The vcpu can run. but it can't hide. */ +} + +static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1) +{ + u64 reg; + + /* SPE present on this CPU? */ + if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1), + ID_AA64DFR0_PMSVER_SHIFT)) + return; + + /* Yes; is it owned by EL3? */ + reg = read_sysreg_s(PMBIDR_EL1); + if (reg & PMBIDR_EL1_P) + return; + + /* No; is the host actually using the thing? */ + reg = read_sysreg_s(PMBLIMITR_EL1); + if (!(reg & PMBLIMITR_EL1_E)) + return; + + /* Yes; save the control register and disable data generation */ + *pmscr_el1 = read_sysreg_s(PMSCR_EL1); + write_sysreg_s(0, PMSCR_EL1); + isb(); + + /* Now drain all buffered data to memory */ + psb_csync(); + dsb(nsh); +} + +static hyp_alternate_select(__debug_save_spe, + __debug_save_spe_nvhe, __debug_save_spe_vhe, + ARM64_HAS_VIRT_HOST_EXTN); + +static void __hyp_text __debug_restore_spe(u64 pmscr_el1) +{ + if (!pmscr_el1) + return; + + /* The host page table is installed, but not yet synchronised */ + isb(); + + /* Re-enable data generation */ + write_sysreg_s(pmscr_el1, PMSCR_EL1); +} + void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu, struct kvm_guest_debug_arch *dbg, struct kvm_cpu_context *ctxt) @@ -118,13 +178,15 @@ void __hyp_text __debug_cond_save_host_state(struct kvm_vcpu *vcpu) (vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_MDE)) vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; - __debug_save_state(vcpu, &vcpu->arch.host_debug_state, + __debug_save_state(vcpu, &vcpu->arch.host_debug_state.regs, kern_hyp_va(vcpu->arch.host_cpu_context)); + __debug_save_spe()(&vcpu->arch.host_debug_state.pmscr_el1); } void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu) { - __debug_restore_state(vcpu, &vcpu->arch.host_debug_state, + __debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1); + __debug_restore_state(vcpu, &vcpu->arch.host_debug_state.regs, kern_hyp_va(vcpu->arch.host_cpu_context)); if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 75e83dd40d43..aede1658aeda 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -103,7 +103,13 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) static void __hyp_text __deactivate_traps_vhe(void) { extern char vectors[]; /* kernel exception vectors */ + u64 mdcr_el2 = read_sysreg(mdcr_el2); + mdcr_el2 &= MDCR_EL2_HPMN_MASK | + MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT | + MDCR_EL2_TPMS; + + write_sysreg(mdcr_el2, mdcr_el2); write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); write_sysreg(CPACR_EL1_FPEN, cpacr_el1); write_sysreg(vectors, vbar_el1); @@ -111,6 +117,12 @@ static void __hyp_text __deactivate_traps_vhe(void) static void __hyp_text __deactivate_traps_nvhe(void) { + u64 mdcr_el2 = read_sysreg(mdcr_el2); + + mdcr_el2 &= MDCR_EL2_HPMN_MASK; + mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; + + write_sysreg(mdcr_el2, mdcr_el2); write_sysreg(HCR_RW, hcr_el2); write_sysreg(CPTR_EL2_DEFAULT, cptr_el2); } @@ -132,7 +144,6 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) __deactivate_traps_arch()(); write_sysreg(0, hstr_el2); - write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2); write_sysreg(0, pmuserenr_el0); } @@ -357,6 +368,10 @@ again: } __debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt); + /* + * This must come after restoring the host sysregs, since a non-VHE + * system may enable SPE here and make use of the TTBRs. + */ __debug_cond_restore_host_state(vcpu); return exit_code; diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 88e2f2b938f0..e8e7ba2bc11f 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -16,6 +16,7 @@ */ #include <asm/kvm_hyp.h> +#include <asm/tlbflush.h> void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { @@ -32,7 +33,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) * whole of Stage-1. Weep... */ ipa >>= 12; - asm volatile("tlbi ipas2e1is, %0" : : "r" (ipa)); + __tlbi(ipas2e1is, ipa); /* * We have to ensure completion of the invalidation at Stage-2, @@ -41,7 +42,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) * the Stage-1 invalidation happened first. */ dsb(ish); - asm volatile("tlbi vmalle1is" : : ); + __tlbi(vmalle1is); dsb(ish); isb(); @@ -57,7 +58,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) write_sysreg(kvm->arch.vttbr, vttbr_el2); isb(); - asm volatile("tlbi vmalls12e1is" : : ); + __tlbi(vmalls12e1is); dsb(ish); isb(); @@ -72,7 +73,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) write_sysreg(kvm->arch.vttbr, vttbr_el2); isb(); - asm volatile("tlbi vmalle1" : : ); + __tlbi(vmalle1); dsb(nsh); isb(); @@ -82,7 +83,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) void __hyp_text __kvm_flush_vm_context(void) { dsb(ishst); - asm volatile("tlbi alle1is \n" - "ic ialluis ": : ); + __tlbi(alle1is); + asm volatile("ic ialluis" : : ); dsb(ish); } diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index e703fb9defad..9b0ba191e48e 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -6,6 +6,8 @@ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM64_PTDUMP_CORE) += dump.o obj-$(CONFIG_ARM64_PTDUMP_DEBUGFS) += ptdump_debugfs.o obj-$(CONFIG_NUMA) += numa.o +obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o +KASAN_SANITIZE_physaddr.o += n obj-$(CONFIG_KASAN) += kasan_init.o KASAN_SANITIZE_kasan_init.o := n diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 4c63cb154859..68634c630cdd 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -79,6 +79,13 @@ void verify_cpu_asid_bits(void) } } +static void set_reserved_asid_bits(void) +{ + if (IS_ENABLED(CONFIG_QCOM_FALKOR_ERRATUM_1003) && + cpus_have_const_cap(ARM64_WORKAROUND_QCOM_FALKOR_E1003)) + __set_bit(FALKOR_RESERVED_ASID, asid_map); +} + static void flush_context(unsigned int cpu) { int i; @@ -87,6 +94,8 @@ static void flush_context(unsigned int cpu) /* Update the list of reserved ASIDs and the ASID bitmap. */ bitmap_clear(asid_map, 0, NUM_USER_ASIDS); + set_reserved_asid_bits(); + /* * Ensure the generation bump is observed before we xchg the * active_asids. @@ -244,6 +253,8 @@ static int asids_init(void) panic("Failed to allocate bitmap for %lu ASIDs\n", NUM_USER_ASIDS); + set_reserved_asid_bits(); + pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS); return 0; } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 4a14b25163fb..351f7595cb3e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -211,7 +211,8 @@ static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, dma_addr_t dev_addr; dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs); - if (!is_device_dma_coherent(dev)) + if (!is_device_dma_coherent(dev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); return dev_addr; @@ -222,7 +223,8 @@ static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (!is_device_dma_coherent(dev)) + if (!is_device_dma_coherent(dev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir); swiotlb_unmap_page(dev, dev_addr, size, dir, attrs); } @@ -235,7 +237,8 @@ static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int i, ret; ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs); - if (!is_device_dma_coherent(dev)) + if (!is_device_dma_coherent(dev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) for_each_sg(sgl, sg, ret, i) __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), sg->length, dir); @@ -251,7 +254,8 @@ static void __swiotlb_unmap_sg_attrs(struct device *dev, struct scatterlist *sg; int i; - if (!is_device_dma_coherent(dev)) + if (!is_device_dma_coherent(dev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) for_each_sg(sgl, sg, nelems, i) __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)), sg->length, dir); @@ -352,6 +356,13 @@ static int __swiotlb_dma_supported(struct device *hwdev, u64 mask) return 1; } +static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr) +{ + if (swiotlb) + return swiotlb_dma_mapping_error(hwdev, addr); + return 0; +} + static struct dma_map_ops swiotlb_dma_ops = { .alloc = __dma_alloc, .free = __dma_free, @@ -366,7 +377,7 @@ static struct dma_map_ops swiotlb_dma_ops = { .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu, .sync_sg_for_device = __swiotlb_sync_sg_for_device, .dma_supported = __swiotlb_dma_supported, - .mapping_error = swiotlb_dma_mapping_error, + .mapping_error = __swiotlb_dma_mapping_error, }; static int __init atomic_pool_init(void) @@ -830,14 +841,21 @@ static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops, * then the IOMMU core will have already configured a group for this * device, and allocated the default domain for that group. */ - if (!domain || iommu_dma_init_domain(domain, dma_base, size, dev)) { - pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", - dev_name(dev)); - return false; + if (!domain) + goto out_err; + + if (domain->type == IOMMU_DOMAIN_DMA) { + if (iommu_dma_init_domain(domain, dma_base, size, dev)) + goto out_err; + + dev->archdata.dma_ops = &iommu_dma_ops; } - dev->archdata.dma_ops = &iommu_dma_ops; return true; +out_err: + pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", + dev_name(dev)); + return false; } static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 156169c6981b..81283851c9af 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -691,17 +691,3 @@ int cpu_enable_pan(void *__unused) return 0; } #endif /* CONFIG_ARM64_PAN */ - -#ifdef CONFIG_ARM64_UAO -/* - * Kernel threads have fs=KERNEL_DS by default, and don't need to call - * set_fs(), devtmpfs in particular relies on this behaviour. - * We need to enable the feature at runtime (instead of adding it to - * PSR_MODE_EL1h) as the feature may not be implemented by the cpu. - */ -int cpu_enable_uao(void *__unused) -{ - asm(SET_PSTATE_UAO(1)); - return 0; -} -#endif /* CONFIG_ARM64_UAO */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 380ebe705093..e19e06593e37 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -36,6 +36,7 @@ #include <linux/efi.h> #include <linux/swiotlb.h> #include <linux/vmalloc.h> +#include <linux/mm.h> #include <asm/boot.h> #include <asm/fixmap.h> @@ -209,8 +210,8 @@ void __init arm64_memblock_init(void) * linear mapping. Take care not to clip the kernel which may be * high in memory. */ - memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa(_end)), - ULLONG_MAX); + memblock_remove(max_t(u64, memstart_addr + linear_region_size, + __pa_symbol(_end)), ULLONG_MAX); if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) { /* ensure that memstart_addr remains sufficiently aligned */ memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size, @@ -225,7 +226,7 @@ void __init arm64_memblock_init(void) */ if (memory_limit != (phys_addr_t)ULLONG_MAX) { memblock_mem_limit_remove_map(memory_limit); - memblock_add(__pa(_text), (u64)(_end - _text)); + memblock_add(__pa_symbol(_text), (u64)(_end - _text)); } if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) { @@ -278,7 +279,7 @@ void __init arm64_memblock_init(void) * Register the kernel text, kernel data, initrd, and initial * pagetables with memblock. */ - memblock_reserve(__pa(_text), _end - _text); + memblock_reserve(__pa_symbol(_text), _end - _text); #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start) { memblock_reserve(initrd_start, initrd_end - initrd_start); @@ -486,7 +487,8 @@ void __init mem_init(void) void free_initmem(void) { - free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)), + free_reserved_area(lm_alias(__init_begin), + lm_alias(__init_end), 0, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index 01e88c8bcab0..c4c8cd4c31d4 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -88,7 +88,7 @@ void __iounmap(volatile void __iomem *io_addr) * We could get an address outside vmalloc range in case * of ioremap_cache() reusing a RAM mapping. */ - if (VMALLOC_START <= addr && addr < VMALLOC_END) + if (is_vmalloc_addr((void *)addr)) vunmap((void *)addr); } EXPORT_SYMBOL(__iounmap); diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 757009daa9ed..201d918e7575 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/memblock.h> #include <linux/start_kernel.h> +#include <linux/mm.h> #include <asm/mmu_context.h> #include <asm/kernel-pgtable.h> @@ -26,6 +27,13 @@ static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); +/* + * The p*d_populate functions call virt_to_phys implicitly so they can't be used + * directly on kernel symbols (bm_p*d). All the early functions are called too + * early to use lm_alias so __p*d_populate functions must be used to populate + * with the physical address from __pa_symbol. + */ + static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end) { @@ -33,12 +41,12 @@ static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long next; if (pmd_none(*pmd)) - pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); + __pmd_populate(pmd, __pa_symbol(kasan_zero_pte), PMD_TYPE_TABLE); pte = pte_offset_kimg(pmd, addr); do { next = addr + PAGE_SIZE; - set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page), + set_pte(pte, pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL)); } while (pte++, addr = next, addr != end && pte_none(*pte)); } @@ -51,7 +59,7 @@ static void __init kasan_early_pmd_populate(pud_t *pud, unsigned long next; if (pud_none(*pud)) - pud_populate(&init_mm, pud, kasan_zero_pmd); + __pud_populate(pud, __pa_symbol(kasan_zero_pmd), PMD_TYPE_TABLE); pmd = pmd_offset_kimg(pud, addr); do { @@ -68,7 +76,7 @@ static void __init kasan_early_pud_populate(pgd_t *pgd, unsigned long next; if (pgd_none(*pgd)) - pgd_populate(&init_mm, pgd, kasan_zero_pud); + __pgd_populate(pgd, __pa_symbol(kasan_zero_pud), PUD_TYPE_TABLE); pud = pud_offset_kimg(pgd, addr); do { @@ -148,7 +156,7 @@ void __init kasan_init(void) */ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); dsb(ishst); - cpu_replace_ttbr1(tmp_pg_dir); + cpu_replace_ttbr1(lm_alias(tmp_pg_dir)); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); @@ -199,10 +207,10 @@ void __init kasan_init(void) */ for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_zero_pte[i], - pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); + pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); memset(kasan_zero_page, 0, PAGE_SIZE); - cpu_replace_ttbr1(swapper_pg_dir); + cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 17243e43184e..b805c017f789 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -28,6 +28,7 @@ #include <linux/memblock.h> #include <linux/fs.h> #include <linux/io.h> +#include <linux/mm.h> #include <asm/barrier.h> #include <asm/cputype.h> @@ -359,8 +360,8 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) { - unsigned long kernel_start = __pa(_text); - unsigned long kernel_end = __pa(__init_begin); + phys_addr_t kernel_start = __pa_symbol(_text); + phys_addr_t kernel_end = __pa_symbol(__init_begin); /* * Take care not to create a writable alias for the @@ -427,14 +428,14 @@ void mark_rodata_ro(void) unsigned long section_size; section_size = (unsigned long)_etext - (unsigned long)_text; - create_mapping_late(__pa(_text), (unsigned long)_text, + create_mapping_late(__pa_symbol(_text), (unsigned long)_text, section_size, PAGE_KERNEL_ROX); /* * mark .rodata as read only. Use __init_begin rather than __end_rodata * to cover NOTES and EXCEPTION_TABLE. */ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata; - create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata, + create_mapping_late(__pa_symbol(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); /* flush the TLBs after updating live kernel mappings */ @@ -446,7 +447,7 @@ void mark_rodata_ro(void) static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma) { - phys_addr_t pa_start = __pa(va_start); + phys_addr_t pa_start = __pa_symbol(va_start); unsigned long size = va_end - va_start; BUG_ON(!PAGE_ALIGNED(pa_start)); @@ -494,7 +495,7 @@ static void __init map_kernel(pgd_t *pgd) */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START), - __pud(__pa(bm_pmd) | PUD_TYPE_TABLE)); + __pud(__pa_symbol(bm_pmd) | PUD_TYPE_TABLE)); pud_clear_fixmap(); } else { BUG(); @@ -524,8 +525,8 @@ void __init paging_init(void) * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); - memcpy(swapper_pg_dir, pgd, PAGE_SIZE); - cpu_replace_ttbr1(swapper_pg_dir); + memcpy(swapper_pg_dir, pgd, PGD_SIZE); + cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); pgd_clear_fixmap(); memblock_free(pgd_phys, PAGE_SIZE); @@ -534,7 +535,7 @@ void __init paging_init(void) * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd * allocated with it. */ - memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE, + memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE, SWAPPER_DIR_SIZE - PAGE_SIZE); } @@ -645,6 +646,12 @@ static inline pte_t * fixmap_pte(unsigned long addr) return &bm_pte[pte_index(addr)]; } +/* + * The p*d_populate functions call virt_to_phys implicitly so they can't be used + * directly on kernel symbols (bm_p*d). This function is called too early to use + * lm_alias so __p*d_populate functions must be used to populate with the + * physical address from __pa_symbol. + */ void __init early_fixmap_init(void) { pgd_t *pgd; @@ -654,7 +661,7 @@ void __init early_fixmap_init(void) pgd = pgd_offset_k(addr); if (CONFIG_PGTABLE_LEVELS > 3 && - !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa(bm_pud))) { + !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on @@ -663,12 +670,14 @@ void __init early_fixmap_init(void) BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); pud = pud_offset_kimg(pgd, addr); } else { - pgd_populate(&init_mm, pgd, bm_pud); + if (pgd_none(*pgd)) + __pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE); pud = fixmap_pud(addr); } - pud_populate(&init_mm, pud, bm_pmd); + if (pud_none(*pud)) + __pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE); pmd = fixmap_pmd(addr); - pmd_populate_kernel(&init_mm, pmd, bm_pte); + __pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE); /* * The boot-ioremap range spans multiple pmds, for which diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c new file mode 100644 index 000000000000..91371daf397c --- /dev/null +++ b/arch/arm64/mm/physaddr.c @@ -0,0 +1,30 @@ +#include <linux/bug.h> +#include <linux/export.h> +#include <linux/types.h> +#include <linux/mmdebug.h> +#include <linux/mm.h> + +#include <asm/memory.h> + +phys_addr_t __virt_to_phys(unsigned long x) +{ + WARN(!__is_lm_address(x), + "virt_to_phys used for non-linear address: %pK (%pS)\n", + (void *)x, + (void *)x); + + return __virt_to_phys_nodebug(x); +} +EXPORT_SYMBOL(__virt_to_phys); + +phys_addr_t __phys_addr_symbol(unsigned long x) +{ + /* + * This is bounds checking against the kernel image only. + * __pa_symbol should only be used on kernel symbol addresses. + */ + VIRTUAL_BUG_ON(x < (unsigned long) KERNEL_START || + x > (unsigned long) KERNEL_END); + return __pa_symbol_nodebug(x); +} +EXPORT_SYMBOL(__phys_addr_symbol); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 32682be978e0..cd4d53d7e458 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -138,6 +138,7 @@ ENDPROC(cpu_do_resume) * - pgd_phys - physical address of new TTB */ ENTRY(cpu_do_switch_mm) + pre_ttbr0_update_workaround x0, x1, x2 mmid x1, x1 // get mm->context.id bfi x0, x1, #48, #16 // set the ASID msr ttbr0_el1, x0 // set TTBR0 |